Papers by Yubin Kim

4 papers
Don’t Miss the Forest for the Trees: Attentional Vision Calibration for Large Vision Language Models (2025.findings-acl)

Copied to clipboard

Challenge: Large Vision Language Models suffer from hallucinations, attributing incorrect or misleading features to images.
Approach: They propose a test-time approach that recalibrates the influence of blind tokens . they identify blind token by analyzing layer-wise attention distributions over image tokens.
Outcome: The proposed approach reduces hallucinations in large vision language models . it uses a contrastive decoding strategy to balance the influence of blind tokens .
FinHarmBench: Financial Jailbreak Benchmark and Unsupervised Safety Fine-Tuning via Refusal Steering Distillation (2026.acl-industry)

Copied to clipboard

Challenge: Existing safety benchmarks focus on general harms and lack the granularity needed to capture domain-specific financial threats.
Approach: They propose a benchmark to evaluate financially harmful and confusable benign prompts.
Outcome: The proposed framework improves refusal behavior without annotating refusal responses.
BehaviorSFT: Behavioral Token Conditioning for Health Agents Across the Proactivity Spectrum (2025.findings-emnlp)

Copied to clipboard

Challenge: Large Language Models (LLMs) struggle with proactive engagement, authors say . a blind clinical evaluation confirmed that trained agents exhibit more realistic clinical behavior .
Approach: They propose a training strategy using behavioral tokens to explicitly condition LLMs for dynamic behavioral selection.
Outcome: The proposed training strategy boosts performance on both benchmarks.
EmpathicStories++: A Multimodal Dataset for Empathy Towards Personal Experiences (2024.findings-acl)

Copied to clipboard

Challenge: Existing datasets for empathy modeling are limited in the ways they are not captured in the wild.
Approach: They propose a multimodal dataset for empathy during personal experience sharing that contains 53 hours of video, audio, and text data of 41 participants.
Outcome: The EmpathicStories++ dataset contains 53 hours of video, audio, and text data of 41 participants sharing vulnerable experiences and reading empathically resonant stories with an AI agent.

What is GenGO?

GenGO is an NLP powered publication search system. It currenctly indexes 30k+ papers from ACL Anthology, and implements multi-aspect summarization, semantic search, and more!

Information

About
Limitations